arch-review

arch-review is a command for Claude Code from strikersam/autonomous-ai-agency. It costs 0 tokens per session (654 once invoked), scanned A, original, MIT.

A command for reviewing software architecture and technical debt, which is the cost of design shortcuts that make future changes harder. It examines module boundaries, dependencies, circular imports, and oversized files.

In plain words
What is it for?
Use it before multi-file features, when adding modules, during architecture reviews, or when files and dependencies are becoming difficult to manage.
Why use it?
It helps expose structural problems before a new feature makes them more difficult and expensive to fix.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

Good fit Use it before multi-file features, when adding modules, during architecture reviews, or when files and dependencies are becoming difficult to manage.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/strikersam/autonomous-ai-agency/arch-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for arch-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/strikersam/autonomous-ai-agency/arch-review/github.svg)](https://agentmods.dev/commands/strikersam/autonomous-ai-agency/arch-review)
Your own site
<a href="https://agentmods.dev/commands/strikersam/autonomous-ai-agency/arch-review"><img src="https://agentmods.dev/badge/commands/strikersam/autonomous-ai-agency/arch-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for arch-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/strikersam/autonomous-ai-agency/arch-review"><img src="https://agentmods.dev/badge/commands/strikersam/autonomous-ai-agency/arch-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 654 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00654
Opus 5 $0.00000 $0.00327
Sonnet 5 $0.00000 $0.00131
Haiku 4.5 $0.00000 $0.00065

Measured 9d ago against content hash 7807da071360, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

arch-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/arch-review.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/arch-review — Architecture Agent

Review architectural decisions, identify technical debt, and propose improvements.

When to use

  • Before planning a multi-file feature (use with /plan)
  • Monthly architecture review
  • When a file exceeds 800 lines
  • When adding a new module or package

Steps

  1. Read current architecture

    • Read audit/architecture.md for the baseline
    • Read audit/technical-debt.md for open debt items
    • Run graphify query "architecture overview" for current state
  2. Identify the change scope

    git diff --name-only main..HEAD
    

    Map changed files to the architecture layers in AGENTS.md.

  3. Module boundary check

    • Does the change respect existing module boundaries?
    • Are new abstractions introduced? Are they necessary?
    • Does any file now exceed 800 lines?
  4. Dependency direction check

    • Does the change introduce circular imports?
    • Does the change add a dependency from a lower layer to a higher layer?
    python -c "
    import ast, sys
    from pathlib import Path
    # Quick circular import detector
    for f in Path('.').glob('*.py'):
        try:
            src = f.read_text()
            tree = ast.parse(src)
            imports = [n.names[0].name if isinstance(n, ast.Import) else n.module
                      for n in ast.walk(tree) 
                      if isinstance(n, (ast.Import, ast.ImportFrom)) and n.module]
            # Flag proxy importing from backend
            if 'backend' in str(f) and 'proxy' in str(imports):
                print(f'WARNING: {f} imports from proxy (reverse dependency)')
        except: pass
    "
    
  5. Technical debt impact

    • Will this change increase or decrease technical debt?
    • If it increases debt (e.g., adds to a god file), create a follow-up issue
  6. ADR requirement check

    • Does this change a fundamental architectural decision?
    • If yes, draft an ADR in docs/adrs/
  7. Report Format: "Architecture review for [scope]: [PASS|CONCERN|BLOCK]"

    • PASS: change is architecturally sound
    • CONCERN: change is acceptable but creates debt (document in PR description)
    • BLOCK: change violates architectural principles (must be redesigned)

Read the full file on GitHub · 73 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 73 lines · 0 tokens per session scan A 7807da071360

Subscribe to this mod's changes

arch-review is a command published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 654 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.